Searcharxiv⌕ Search

arXiv subjects

Soyeon Kim

Publications and source records attributed to Soyeon Kim.

35 records · Page 2Linked to original sources
arXiv2025

From KMMLU-Redux to KMMLU-Pro: A Professional Korean Benchmark Suite for LLM Evaluation

The development of Large Language Models (LLMs) requires robust benchmarks that encompass not only academic domains but also industrial fields to effectively evaluate their applicability in real-world scenarios. In this paper, we introduce two Korean expert-level benchmarks. KMMLU-Redux, reconstructed from the existing KMMLU, consists of questions from the Korean National Technical Qualification exams, with critical errors removed to enhance reliability. KMMLU-Pro is based on Korean National Professional Licensure exams to reflect professional knowledge in Korea. Our experiments demonstrate that these benchmarks comprehensively represent industrial knowledge in Korea. We release our dataset publicly available.

cs.CL↗
arXiv2025

DNA Nanotechnology for Superradiance

Superradiance, first proposed by Dicke in 1954, is a highly efficient quantum light source that differs from conventional spontaneous emission. Unlike typical spontaneous emission, where intensity scales linearly with the number of electric dipoles, superradiance exhibits an intensity that scales quadratically with the number of electric dipoles. Similarly, the decay rate also increases proportionally to the dipole numbers. This collective emission is especially powerful when it manifests as superfluorescence, a physical regime of superradiance where spontaneously emerging coherence is achieved by arranging excited dipoles in the same orientation within a volume much smaller than their emission wavelength. Numerous experimental strategies have been employed to generate superradiance, with one common approach being the use of stochastically formed aggregates of quantum dots and organic dyes. However, the inherent randomness in such systems prevents precise control over the number, spatial distribution, and relative orientation of the emitters. This often leads to non-uniform coupling strengths and parasitic dephasing effects, which make it difficult to predict the resulting quantum emission and limit its use in engineered devices. A deterministic platform that provides precise control over these parameters is therefore essential for realizing the full potential of superradiant systems. Here, we (i) specifically outline the advantages of DNA nanotechnology in tackling this challenge, (ii) discuss the reasons why superradiance has not yet been realized even with the state-of-the art DNA nanotechnology, and (iii) propose potential solutions for overcoming the current limitations.

quant-ph↗
arXiv2025

NEXT-EVAL: Next Evaluation of Traditional and LLM Web Data Record Extraction

Effective evaluation of web data record extraction methods is crucial, yet hampered by static, domain-specific benchmarks and opaque scoring practices. This makes fair comparison between traditional algorithmic techniques, which rely on structural heuristics, and Large Language Model (LLM)-based approaches, offering zero-shot extraction across diverse layouts, particularly challenging. To overcome these limitations, we introduce a concrete evaluation framework. Our framework systematically generates evaluation datasets from arbitrary MHTML snapshots, annotates XPath-based supervision labels, and employs structure-aware metrics for consistent scoring, specifically preventing text hallucination and allowing only for the assessment of positional hallucination. It also incorporates preprocessing strategies to optimize input for LLMs while preserving DOM semantics: HTML slimming, Hierarchical JSON, and Flat JSON. Additionally, we created a publicly available synthetic dataset by transforming DOM structures and modifying content. We benchmark deterministic heuristic algorithms and off-the-shelf LLMs across these multiple input formats. Our benchmarking shows that Flat JSON input enables LLMs to achieve superior extraction accuracy (F1 score of 0.9567) and minimal hallucination compared to other input formats like Slimmed HTML and Hierarchical JSON. We establish a standardized foundation for rigorous benchmarking, paving the way for the next principled advancements in web data record extraction.

cs.DB↗
arXiv2025

Splicing braid varieties

For a positive braid $β\in \mathrm{Br}^{+}_{k}$, we consider the braid variety $X(β)$. We define a family of open sets $\mathcal{U}_{r, w}$ in $X(β)$, where $w \in S_k$ is a permutation and $r$ is a positive integer no greater than the length of $β$. For fixed $r$, the sets $\mathcal{U}_{r, w}$ form an open cover of $X(β)$. We conjecture that $\mathcal{U}_{r,w}$ is given by the nonvanishing of some cluster variables in a single cluster for the cluster structure on $\mathbb{C}[X(β)]$ and that $\mathcal{U}_{r,w}$ admits a cluster structure given by freezing these variables. Moreover, we show that $\mathcal{U}_{r, w}$ is always isomorphic to the product of two braid varieties, and we conjecture that this isomorphism is quasi-cluster. In some important special cases, we are able to prove our conjectures.

math.AG↗
arXiv2025

Conditional Temporal Neural Processes with Covariance Loss

We introduce a novel loss function, Covariance Loss, which is conceptually equivalent to conditional neural processes and has a form of regularization so that is applicable to many kinds of neural networks. With the proposed loss, mappings from input variables to target variables are highly affected by dependencies of target variables as well as mean activation and mean dependencies of input and target variables. This nature enables the resulting neural networks to become more robust to noisy observations and recapture missing dependencies from prior information. In order to show the validity of the proposed loss, we conduct extensive sets of experiments on real-world datasets with state-of-the-art models and discuss the benefits and drawbacks of the proposed Covariance Loss.

cs.LG↗
arXiv2025

Explainable AI-Based Interface System for Weather Forecasting Model

Machine learning (ML) is becoming increasingly popular in meteorological decision-making. Although the literature on explainable artificial intelligence (XAI) is growing steadily, user-centered XAI studies have not extend to this domain yet. This study defines three requirements for explanations of black-box models in meteorology through user studies: statistical model performance for different rainfall scenarios to identify model bias, model reasoning, and the confidence of model outputs. Appropriate XAI methods are mapped to each requirement, and the generated explanations are tested quantitatively and qualitatively. An XAI interface system is designed based on user feedback. The results indicate that the explanations increase decision utility and user trust. Users prefer intuitive explanations over those based on XAI algorithms even for potentially easy-to-recognize examples. These findings can provide evidence for future research on user-centered XAI algorithms, as well as a basis to improve the usability of AI systems in practice.

cs.AI↗
arXiv2025

Example-Based Concept Analysis Framework for Deep Weather Forecast Models

To improve the trustworthiness of an AI model, finding consistent, understandable representations of its inference process is essential. This understanding is particularly important in high-stakes operations such as weather forecasting, where the identification of underlying meteorological mechanisms is as critical as the accuracy of the predictions. Despite the growing literature that addresses this issue through explainable AI, the applicability of their solutions is often limited due to their AI-centric development. To fill this gap, we follow a user-centric process to develop an example-based concept analysis framework, which identifies cases that follow a similar inference process as the target instance in a target model and presents them in a user-comprehensible format. Our framework provides the users with visually and conceptually analogous examples, including the probability of concept assignment to resolve ambiguities in weather mechanisms. To bridge the gap between vector representations identified from models and human-understandable explanations, we compile a human-annotated concept dataset and implement a user interface to assist domain experts involved in the the framework development.

cs.AI↗
arXiv2025

Splicing skew shaped positroids

Skew shaped positroids (or skew shaped positroid varieties) are certain Richardson varieties in the flag variety that admit a realization as explicit subvarieties of the Grassmannian $\mathrm{Gr}(k,n)$. They are parametrized by a pair of Young diagrams $μ\subseteq λ$ fitting inside a $k \times (n-k)$-rectangle. For every $a = 1, \dots, n-k$, we define an explicit open set $U_a$ inside the skew shaped positroid $S^{\circ}_{λ/μ}$, and show that $U_a$ is isomorphic to the product of two smaller skew shaped positroids. Moreover, $U_a$ admits a natural cluster structure and the aforementioned isomorphism is quasi-cluster in the sense of Fraser. Our methods depend on realizing the skew shaped positroid as an explicit braid variety, and generalize the work of the first and third authors for open positroid cells in the Grassmannian.

math.AG↗
arXiv2025

PFGuard: A Generative Framework with Privacy and Fairness Safeguards

Generative models must ensure both privacy and fairness for Trustworthy AI. While these goals have been pursued separately, recent studies propose to combine existing privacy and fairness techniques to achieve both goals. However, naively combining these techniques can be insufficient due to privacy-fairness conflicts, where a sample in a minority group may be represented in ways that support fairness, only to be suppressed for privacy. We demonstrate how these conflicts lead to adverse effects, such as privacy violations and unexpected fairness-utility tradeoffs. To mitigate these risks, we propose PFGuard, a generative framework with privacy and fairness safeguards, which simultaneously addresses privacy, fairness, and utility. By using an ensemble of multiple teacher models, PFGuard balances privacy-fairness conflicts between fair and private training stages and achieves high utility based on ensemble learning. Extensive experiments show that PFGuard successfully generates synthetic data on high-dimensional data while providing both DP guarantees and convergence in fair generative modeling.

cs.LG↗
arXiv2025

Diverse Rare Sample Generation with Pretrained GANs

Deep generative models are proficient in generating realistic data but struggle with producing rare samples in low density regions due to their scarcity of training datasets and the mode collapse problem. While recent methods aim to improve the fidelity of generated samples, they often reduce diversity and coverage by ignoring rare and novel samples. This study proposes a novel approach for generating diverse rare samples from high-resolution image datasets with pretrained GANs. Our method employs gradient-based optimization of latent vectors within a multi-objective framework and utilizes normalizing flows for density estimation on the feature space. This enables the generation of diverse rare images, with controllable parameters for rarity, diversity, and similarity to a reference image. We demonstrate the effectiveness of our approach both qualitatively and quantitatively across various datasets and GANs without retraining or fine-tuning the pretrained GANs.

cs.CV↗
arXiv2024

ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models

Large language models (LLMs) have achieved unprecedented performances in various applications, yet evaluating them is still challenging. Existing benchmarks are either manually constructed or are automatic, but lack the ability to evaluate the thought process of LLMs with arbitrary complexity. We contend that utilizing existing relational databases based on the entity-relationship (ER) model is a promising approach for constructing benchmarks as they contain structured knowledge that can be used to question LLMs. Unlike knowledge graphs, which are also used to evaluate LLMs, relational databases have integrity constraints that can be used to better construct complex in-depth questions and verify answers: (1) functional dependencies can be used to pinpoint critical keywords that an LLM must know to properly answer a given question containing certain attribute values; and (2) foreign key constraints can be used to join relations and construct multi-hop questions, which can be arbitrarily long and used to debug intermediate answers. We thus propose ERBench, which uses these integrity constraints to convert any database into an LLM benchmark. ERBench supports continuous evaluation as databases change, multimodal questions, and various prompt engineering techniques. In our experiments, we construct LLM benchmarks using databases of multiple domains and make an extensive comparison of contemporary LLMs. We show how ERBench can properly evaluate any LLM by not only checking for answer correctness, but also effectively verifying the rationales by looking for the right keywords.

cs.CL↗
arXiv2024

First Demonstration of HZO/beta-Ga2O3 Ferroelectric FinFET with Improved Memory Window

We have experimentally demonstrated the effectiveness of beta-gallium oxide (beta-Ga2O3) ferroelectric fin field-effect transistors (Fe-FinFETs) for the first time. Atomic layer deposited (ALD) hafnium zirconium oxide (HZO) is used as the ferroelectric layer. The HZO/beta-Ga2O3 Fe-FinFETs have wider counterclockwise hysteresis loops in the transfer characteristics than that of conventional planar FET, achieving record-high memory window (MW) of 13.9 V in a single HZO layer. When normalized to the actual channel width, FinFETs show an improved ION/IOFF ratio of 2.3x10^7 and a subthreshold swing value of 110 mV/dec. The enhanced characteristics are attributed to the low-interface state density (Dit), showing good interface properties between the beta-Ga2O3 and HZO layer. The enhanced polarization due to larger electric fields across the entire ferroelectric layer in FinFETs is validated using Sentaurus TCAD. After 5x10^6 program/erase (PGM/ERS) cycles, the MW was maintained at 9.2 V, and the retention time was measured up to 3x10^4 s with low degradation. Therefore, the ultrawide bandgap (UWBG) Fe-FinFET was shown to be one of the promising candidates for high-density non-volatile memory devices.

physics.app-ph↗
arXiv2024

Capsule Neural Networks as Noise Stabilizer for Time Series Data

Capsule Neural Networks utilize capsules, which bind neurons into a single vector and learn position equivariant features, which makes them more robust than original Convolutional Neural Networks. CapsNets employ an affine transformation matrix and dynamic routing with coupling coefficients to learn robustly. In this paper, we investigate the effectiveness of CapsNets in analyzing highly sensitive and noisy time series sensor data. To demonstrate CapsNets robustness, we compare their performance with original CNNs on electrocardiogram data, a medical time series sensor data with complex patterns and noise. Our study provides empirical evidence that CapsNets function as noise stabilizers, as investigated by manual and adversarial attack experiments using the fast gradient sign method and three manual attacks, including offset shifting, gradual drift, and temporal lagging. In summary, CapsNets outperform CNNs in both manual and adversarial attacked data. Our findings suggest that CapsNets can be effectively applied to various sensor systems to improve their resilience to noise attacks. These results have significant implications for designing and implementing robust machine learning models in real world applications. Additionally, this study contributes to the effectiveness of CapsNet models in handling noisy data and highlights their potential for addressing the challenges of noise data in time series analysis.

cs.LG↗
arXiv2022

Vision Transformer Equipped with Neural Resizer on Facial Expression Recognition Task

When it comes to wild conditions, Facial Expression Recognition is often challenged with low-quality data and imbalanced, ambiguous labels. This field has much benefited from CNN based approaches; however, CNN models have structural limitation to see the facial regions in distant. As a remedy, Transformer has been introduced to vision fields with global receptive field, but requires adjusting input spatial size to the pretrained models to enjoy their strong inductive bias at hands. We herein raise a question whether using the deterministic interpolation method is enough to feed low-resolution data to Transformer. In this work, we propose a novel training framework, Neural Resizer, to support Transformer by compensating information and downscaling in a data-driven manner trained with loss function balancing the noisiness and imbalance. Experiments show our Neural Resizer with F-PDLS loss function improves the performance with Transformer variants in general and nearly achieves the state-of-the-art performance.

cs.CV↗
arXiv2022

Two-Step Spike Encoding Scheme and Architecture for Highly Sparse Spiking-Neural-Network

This paper proposes a two-step spike encoding scheme, which consists of the source encoding and the process encoding for a high energy-efficient spiking-neural-network (SNN) acceleration. The eigen-train generation and its superposition generate spike trains which show high accuracy with low spike ratio. Sparsity boosting (SB) and spike generation skipping (SGS) reduce the amount of operations for SNN. Time shrinking multi-level encoding (TS-MLE) compresses the number of spikes in a train along time axis, and spike-level clock skipping (SLCS) decreases the processing time. Eigen-train generation achieves 90.3% accuracy, the same accuracy of CNN, under the condition of 4.18% spike ratio for CIFAR-10 classification. SB reduces spike ratio by 0.49x with only 0.1% accuracy loss, and the SGS reduces the spike ratio by 20.9% with 0.5% accuracy loss. TS-MLE and SLCS increases the throughput of SNN by 2.8x while decreasing the hardware resource for spike generator by 75% compared with previous generators.

cs.AR↗
arXiv2021

Visualization of reaction chemistry in W-KClO4-BaCrO4 delay mixtures via a Sestak-Berggren model based isoconversional method

The combustion delay mixture of tungsten (W), potassium perchlorate (KClO4), and barium chromate (BaCrO4), also known as the WKB mixture, has long been considered to be an integral part of military-grade ammunition. Despite its long history, however, their progressive reaction dynamics remains a question mark, especially due to the complex nature of their combustion reaction. As opposed to a one-step oxidation commonly observed in conventional combustions, the WKB mixture is associated with a multibody reaction between its solid-state components. To this end, the emergence of three combustion peaks, which we corresponded with disparate chemical reactions, was observed using thermogravimetric analysis on two separate WKB mixtures with differing mixture ratios. We applied the stepwise isoconversional method on each of the peaks to match the combustion chemistry it represents to the Sestak-Berggren model and computed the conceptual activation energy. Further plotting the logarithmic pre-exponential factor as a function of the reaction progress, we demonstrate a method of using the plot as an intuitive tool to understand the dynamics of individual reactions that compose multi-step chemical reactions. Our study provides a systematic approach in visualizing the reaction chemistry, thereby strengthening the analytical arsenal against reaction dynamics of combustion compounds in general.

cond-mat.mtrl-sci↗